scienceworld-act
CommunityInteract with ScienceWorld environment
Education & Research#ai agent#simulation#tool use#experimentation#environment interaction#scienceworld
Authorbdambrosio
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill allows an AI agent to interact with and perform actions within a simulated ScienceWorld environment, enabling complex problem-solving and task completion in a scientific context.
Core Features & Use Cases
- Action Execution: Send text commands to the ScienceWorld environment (e.g., "look", "take watering can").
- Observation & Feedback: Receives detailed observations, rewards, and completion status after each action.
- Session Management: Integrates with an active ScienceWorld session managed by an executive node, eliminating the need for explicit session IDs.
- Use Case: An agent can use this Skill to explore a virtual lab, manipulate objects, and conduct experiments to achieve a scientific goal, such as growing a plant.
Quick Start
Use the scienceworld-act skill to look around the current environment.
Dependency Matrix
Required Modules
scienceworld
Components
scripts
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: scienceworld-act Download link: https://github.com/bdambrosio/Cognitive_workbench/archive/main.zip#scienceworld-act Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.